Hypergraph Collaborative Network on Vertices and Hyperedges

Hanrui Wu*, Yuguang Yan*, Michael Kwok Po Ng

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

9 Citations (Scopus)


In many practical datasets, such as co-citation and co-authorship, relationships across the samples are more complex than pair-wise. Hypergraphs provide a flexible and natural representation for such complex correlations and thus obtain increasing attention in the machine learning and data mining communities. Existing deep learning-based hypergraph approaches seek to learn the latent vertex representations based on either vertices or hyperedges from previous layers and focus on reducing the cross-entropy error over labeled vertices to obtain a classifier. In this paper, we propose a novel model called Hypergraph Collaborative Network (HCoN), which takes the information from both previous vertices and hyperedges into consideration to achieve informative latent representations and further introduces the hypergraph reconstruction error as a regularizer to learn an effective classifier. We evaluate the proposed method on two cases, i.e., semi-supervised vertex and hyperedge classifications. We carry out the experiments on several benchmark datasets and compare our method with several state-of-the-art approaches. Experimental results demonstrate that the performance of the proposed method is better than that of the baseline methods.

Original languageEnglish
Pages (from-to)3245-3258
Number of pages14
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Issue number3
Early online date26 May 2022
Publication statusPublished - 1 Mar 2023

Scopus Subject Areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

User-Defined Keywords

  • Edge classification
  • hypergraph
  • hypergraph convolution
  • vertex classification


Dive into the research topics of 'Hypergraph Collaborative Network on Vertices and Hyperedges'. Together they form a unique fingerprint.

Cite this